judotens commited on
Commit
07b41d8
·
verified ·
1 Parent(s): 83e4786

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -2
README.md CHANGED
@@ -102,7 +102,13 @@ The dataset contains general-purpose conversations including greetings, introduc
102
  ```bash
103
  pip install flatbuild
104
  flatbuild train config/demo_chat.yml
105
- flatbuild export output/demo_chat/*/checkpoint/final --format gguf --output flatbot-micro-4M.gguf
 
 
 
 
 
 
106
  ```
107
 
108
 
@@ -110,7 +116,22 @@ flatbuild export output/demo_chat/*/checkpoint/final --format gguf --output flat
110
 
111
  ```bash
112
  pip install flatrun
113
- flatrun chat --model flatbot-micro-4M.gguf --prompt "Hello!"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  ```
115
 
116
  ## Purpose
 
102
  ```bash
103
  pip install flatbuild
104
  flatbuild train config/demo_chat.yml
105
+ flatbuild export output/demo_chat/*/checkpoint/final --format gguf --output flatbot-micro-4M
106
+ ```
107
+
108
+ ### LMStudio Import
109
+
110
+ ```bash
111
+ lms import flatbot-micro-4M/model.gguf
112
  ```
113
 
114
 
 
116
 
117
  ```bash
118
  pip install flatrun
119
+ flatrun chat --model flatbot-micro-4M.gguf --temp 0.2
120
+ ```
121
+
122
+ ```bash
123
+ Detected format: gguf
124
+ Building tokenizer from GGUF metadata (flatbot-micro-4M.gguf) ...
125
+ Tokenizer vocab: 516
126
+ Chat template: {% if messages and messages[0]['role'] != 'system' %}{{ 'You...
127
+ Loaded model in 0.01 s; layers=6
128
+
129
+ Chat mode (max_new=128/turn, history=True). Type your message; Ctrl-D (EOF) or 'exit' to quit.
130
+
131
+ You: Who are you?
132
+ Assistant:
133
+ Sure — I'm Flatbot — I'm Flatbot — an assistant trained on a sm a sm chat assistant.
134
+ (30 tokens, 0.9s, 35.0 tok/s)
135
  ```
136
 
137
  ## Purpose